Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 721 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.8468. Min Act: -0.0000

Data Index: 411684 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.0044. Min Act: -0.0000

Data Index: 905050 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1230334 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1221368 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1157254 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.5081. Min Act: -0.0000

Data Index: 81267 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1167763 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4696. Min Act: -0.0000

Data Index: 598746 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4124. Min Act: -0.0000

Data Index: 481584 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4678. Min Act: -0.0000

Data Index: 291867 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4345. Min Act: -0.0000

Data Index: 540366 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4776. Min Act: -0.0000

Data Index: 250404 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4628. Min Act: -0.0000

Data Index: 159266 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4600. Min Act: 0.0000

Data Index: 825362 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4645. Min Act: -0.0000

Data Index: 582101 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4790. Min Act: -0.0000

Data Index: 93526 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1348162 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4744. Min Act: -0.0000

Data Index: 603352 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4826. Min Act: -0.0000

Data Index: 647233 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.8468. Min Range: -1.8468

Max Act: 0.4941. Min Act: -0.0000

Data Index: 959196 (C4 (Web Text))

Max Activating Token Index: 835